fairseq
https://github.com/facebookresearch/fairseq
Python
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported14 Subscribers
Add a CodeTriage badge to fairseq
Help out
- Issues
- reduce padding overhead when using buckets
- What is the license of the TTS models?
- Pre-training HuBERT - AssertionError: number of labels does not match
- [Speech to speech translation with discrete units] produce almost the same audios from different test audios during inference
- train gpt-13B restore parameters cuda oom
- Does pretrained wav2vec2.0 sensitive to the sampling rate of the audio input?
- don't mbart-large-50-many-to-many-mmt support translate chinese to Turkish？？
- Reproducing Downstream Zero-Shot Performance of FairSeq-MoE models
- fairseq install error
- How to transfer the pretrained bart-base model in fairseq to transformers
- Docs
- Python not yet supported